# Sample Settings Check Report ## Configuration Summary | Component | Count | Tokens (est.) | Status | |-----------|-------|---------------|--------| | MCP Servers | 6 | ~45,000 | ⚠️ High | | Active Skills | 3 | ~1,500 | ✓ OK | | Project Files | 2 | ~2,000 | ✓ OK | | **Baseline Total** | — | ~48,500 | ⚠️ Warning | | **Available** | — | ~151,500 (76%) | Marginal | ## Issues Found ### Critical 1. **GitHub MCP server loading all tools** (~18,000 tokens) - 25+ tools loaded but only 3-4 commonly used - Missing `serverInstructions` ### Warnings 1. **Zapier MCP enabled** (~25,000 tokens) - 50+ tools, rarely used - Consider disabling 2. **Playwright missing serverInstructions** - Tool discovery inefficient - Add: `"serverInstructions": "Browser automation..."` 3. **Custom skill SKILL.md is 1,500 words** - Exceeds 1,000 word recommendation - Move reference data to separate file ## Recommended Actions ### Immediate (save ~35,000 tokens) 1. **Disable Zapier MCP** (saves ~25,000) ```json // Remove or comment out in claude_desktop_config.json // "zapier": { ... } ``` 2. **Add serverInstructions to all servers** (saves ~5,000) ```json "github": { "command": "...", "serverInstructions": "GitHub operations. Use for: repos, issues, PRs. Keywords: github, repo, issue, pull request" } ``` 3. **Refactor long skill** (saves ~1,000) - Move data tables to `references/` directory - Keep SKILL.md under 500 words ### Secondary 4. Consider starting fresh conversations for unrelated tasks 5. Review GitHub usage - if only for viewing, use web instead ## After Optimization | Component | Tokens (est.) | Status | |-----------|---------------|--------| | MCP Servers | ~15,000 | ✓ Good | | Skills + Files | ~2,500 | ✓ Good | | **Baseline Total** | ~17,500 | ✓ Good | | **Available** | ~182,500 (91%) | ✓ Excellent | ## Quick Wins Checklist - [x] Disable Zapier MCP - [x] Add serverInstructions to Playwright - [x] Add serverInstructions to GitHub - [x] Add serverInstructions to Notion - [ ] Refactor jamie-brand skill (move procedures data) - [ ] Review PostgreSQL usage frequency